Safety-Aware Time-Optimal Motion Planning With Uncertain Human State Estimation

Human awareness in robot motion planning is crucial for seamless interaction with humans. Many existing techniques slow down, stop, or change the robot's trajectory locally to avoid collisions Although using information on human's state path phase could reduce future interference movements and make safety stops less frequent, such an approach widespread. This paper proposes a novel embedding human model planner. The method explicitly addresses problem of minimizing execution time, including slowdowns owed proximity For this purpose, it converts speed limits into configuration-space cost functions that drive path's optimization. costmap can be updated based observed predicted human. handle deterministic probabilistic representations independent prediction algorithm. Numerical experimental results industrial collaborative cell demonstrate proposed consistently reduces time avoids unnecessary reductions.